{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:11:31Z","timestamp":1767337891301,"version":"3.40.5"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031776090"},{"type":"electronic","value":"9783031776106"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-77610-6_14","type":"book-chapter","created":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T13:24:54Z","timestamp":1737120294000},"page":"146-156","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["VISAGE: Video Synthesis Using Action Graphs for\u00a0Surgery"],"prefix":"10.1007","author":[{"given":"Yousef","family":"Yeganeh","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rachmadio","family":"Lazuardi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amir","family":"Shamseddin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Emine","family":"Dari","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yash","family":"Thirani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Azade","family":"Farshad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,1,17]]},"reference":[{"key":"14_CR1","unstructured":"Astaraki, M., et al.: AutoPaint: a self-inpainting method for unsupervised anomaly detection. arXiv preprint arXiv:2305.12358 (2023)"},{"key":"14_CR2","unstructured":"Bar, A., et al.: Compositional video synthesis with action graphs. In: Meila, M., Zhang, T. (eds.) Proceedings of the 38th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0139, pp. 662\u2013673. PMLR (2021). https:\/\/proceedings.mlr.press\/v139\/bar21a.html"},{"key":"14_CR3","unstructured":"Blattmann, A., et al.: Stable video diffusion: scaling latent video diffusion models to large datasets (2023)"},{"key":"14_CR4","doi-asserted-by":"crossref","unstructured":"Blattmann, A., et al.: Align your latents: high-resolution video synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 22563\u201322575 (2023)","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhong, K., Wang, F., Wang, H., Zhao, X.: Surgical workflow image generation based on generative adversarial networks. In: 2018 International Conference on Artificial Intelligence and Big Data (ICAIBD), pp. 82\u201386. IEEE (2018)","DOI":"10.1109\/ICAIBD.2018.8396171"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Dhamo, H., et al.: Semantic image manipulation using scene graphs. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5213\u20135222 (2020)","DOI":"10.1109\/CVPR42600.2020.00526"},{"key":"14_CR7","unstructured":"Farshad, A., Musatian, S., Dhamo, H., Navab, N.: MIGS: meta image generation from scene graphs. In: BMVC (2021)"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Farshad, A., Yeganeh, Y., Chi, Y., Shen, C., Ommer, B., Navab, N.: SceneGenie: scene graph guided diffusion models for image synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 88\u201398 (2023)","DOI":"10.1109\/ICCVW60793.2023.00016"},{"key":"14_CR9","unstructured":"Farshad, A., Yeganeh, Y., Dhamo, H., Tombari, F., Navab, N.: DisPositioNet: disentangled pose and identity in semantic image manipulation. In: 33rd British Machine Vision Conference 2022, BMVC 2022, London, UK, 21\u201324 November 2022. BMVA Press (2022). https:\/\/bmvc2022.mpi-inf.mpg.de\/0340.pdf"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Gao, R., Xiong, B., Grauman, K.: Im2Flow: motion hallucination from static images for action recognition. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00622"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Garg, S., Dhamo, H., Farshad, A., Musatian, S., Navab, N., Tombari, F.: Unconditional scene graph generation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 16362\u201316371 (2021)","DOI":"10.1109\/ICCV48922.2021.01605"},{"key":"14_CR12","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural. Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR13","doi-asserted-by":"crossref","unstructured":"Holm, F., Ghazaei, G., Czempiel, T., \u00d6zsoy, E., Saur, S., Navab, N.: Dynamic scene graph representation for surgical video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 81\u201387 (2023)","DOI":"10.1109\/ICCVW60793.2023.00015"},{"key":"14_CR14","doi-asserted-by":"crossref","unstructured":"Hu, Y., Luo, C., Chen, Z.: Make it move: controllable image-to-video generation with text descriptions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01768"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Johnson, J., Gupta, A., Fei-Fei, L.: Image generation from scene graphs. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00133"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"K\u00f6ksal, \u00c7., Ghazaei, G., Holm, F., Farshad, A., Navab, N.: SANGRIA: surgical video scene graph optimization for surgical workflow prediction (2024). https:\/\/arxiv.org\/abs\/2407.20214","DOI":"10.1007\/978-3-031-83243-7_10"},{"key":"14_CR17","doi-asserted-by":"publisher","first-page":"102306","DOI":"10.1016\/j.media.2021.102306","volume":"76","author":"L Maier-Hein","year":"2022","unstructured":"Maier-Hein, L., et al.: Surgical data science-from concepts toward clinical translation. Med. Image Anal. 76, 102306 (2022)","journal-title":"Med. Image Anal."},{"issue":"9","key":"14_CR18","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1038\/s41551-017-0132-7","volume":"1","author":"L Maier-Hein","year":"2017","unstructured":"Maier-Hein, L., et al.: Surgical data science for next-generation interventions. Nat. Biomed. Eng. 1(9), 691\u2013696 (2017)","journal-title":"Nat. Biomed. Eng."},{"key":"14_CR19","doi-asserted-by":"publisher","first-page":"105834","DOI":"10.1016\/j.cmpb.2020.105834","volume":"200","author":"A Marzullo","year":"2021","unstructured":"Marzullo, A., Moccia, S., Catellani, M., Calimeri, F., De Momi, E.: Towards realistic laparoscopic image generation using image-domain translation. Comput. Methods Programs Biomed. 200, 105834 (2021)","journal-title":"Comput. Methods Programs Biomed."},{"key":"14_CR20","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1016\/j.jss.2022.11.008","volume":"283","author":"H Mohamadipanah","year":"2023","unstructured":"Mohamadipanah, H., Kearse, L., Wise, B., Backhus, L., Pugh, C.: Generating rare surgical events using cycleGAN: addressing lack of data for artificial intelligence event recognition. J. Surg. Res. 283, 594\u2013605 (2023)","journal-title":"J. Surg. Res."},{"key":"14_CR21","unstructured":"Moing, G.L., Ponce, J., Schmid, C.: WALDO: future video synthesis using object layer decomposition and parametric flow prediction. In: ICCV (2023)"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Murali, A., et al.: Latent graph representations for critical view of safety assessment. IEEE Trans. Med. Imaging (2023)","DOI":"10.1109\/TMI.2023.3333034"},{"key":"14_CR23","doi-asserted-by":"crossref","unstructured":"Ni, H., Shi, C., Li, K., Huang, S.X., Min, M.R.: Conditional image-to-video generation with latent flow diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18444\u201318455 (2023)","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., et al.: Recognition of instrument-tissue interactions in endoscopic videos via action triplets. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, 4\u20138 October 2020, Part III, pp. 364\u2013374. Springer (2020)","DOI":"10.1007\/978-3-030-59716-0_35"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., et al.: Rendezvous: attention mechanisms for the recognition of surgical action triplets in endoscopic videos. Med. Image Anal. 78, 102433 (2022)","DOI":"10.1016\/j.media.2022.102433"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"\u00d6zsoy, E., \u00d6rnek, E.P., Eck, U., Czempiel, T., Tombari, F., Navab, N.: 4D-or: semantic scene graphs for or domain modeling. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 475\u2013485. Springer (2022)","DOI":"10.1007\/978-3-031-16449-1_45"},{"key":"14_CR27","doi-asserted-by":"crossref","unstructured":"Pan, J., et al.: Video generation from single semantic label map. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.00385"},{"key":"14_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021)"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Sharma, S., Nwoye, C.I., Mutter, D., Padoy, N.: Rendezvous in time: an attention-based temporal fusion approach for surgical triplet recognition. Int. J. Comput. Assist. Radiol. Surg. 1\u20137 (2023)","DOI":"10.1007\/s11548-023-02914-1"},{"key":"14_CR31","unstructured":"Tang, Z., Yang, Z., Zhu, C., Zeng, M., Bansal, M.: Any-to-any generation via composable diffusion. In: Thirty-seventh Conference on Neural Information Processing Systems (2023). https:\/\/openreview.net\/forum?id=2EDqbSCnmF"},{"key":"14_CR32","unstructured":"Unterthiner, T., Van\u00a0Steenkiste, S., Kurach, K., Marinier, R., Michalski, M., Gelly, S.: Towards accurate generative models of video: a new metric & challenges. arXiv preprint arXiv:1812.01717 (2018)"},{"key":"14_CR33","unstructured":"Venkatesh, D.K., et al.: Exploring semantic consistency in unpaired image translation to generate data for surgical applications. Int. J. Comput. Assist. Radiol. Surg. 1\u20139 (2024)"},{"key":"14_CR34","unstructured":"Weissenborn, D., T\u00e4ckstr\u00f6m, O., Uszkoreit, J.: Scaling autoregressive video models. In: International Conference on Learning Representations (2019)"},{"key":"14_CR35","doi-asserted-by":"crossref","unstructured":"Wu, Y., Gao, R., Park, J., Chen, Q.: Future video synthesis with object motion prediction. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00558"},{"key":"14_CR36","unstructured":"Yan, W., Hafner, D., James, S., Abbeel, P.: Temporally consistent video transformer for long-term video prediction (2022)"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Yeganeh, Y., Farshad, A., Navab, N.: Shape-aware masking for inpainting in medical imaging. arXiv preprint arXiv:2207.05787 (2022)","DOI":"10.1007\/978-3-031-46914-5_3"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77610-6_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,8]],"date-time":"2025-05-08T17:28:07Z","timestamp":1746725287000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77610-6_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031776090","9783031776106"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77610-6_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"17 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}